© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88862
    Prev
    Next
    INDEX
    Explanations

    Past tense, described events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è·¨å¢ĥ
    -0.25
     è¾ĵ
    -0.24
    èĮĥ
    -0.24
    åĽ´
    -0.23
    .IntPtr
    -0.23
    伤çĹħ
    -0.23
     commend
    -0.23
    Love
    -0.23
    unday
    -0.23
     claim
    -0.23
    POSITIVE LOGITS
     compared
    0.28
    kü
    0.26
     stripped
    0.26
    åįķçĭ¬
    0.26
    ç½®äºİ
    0.26
    kers
    0.25
    alone
    0.25
    forced
    0.25
    广
    0.25
    ewise
    0.25
    Activations Density 0.015%

    No Known Activations